Multi-agent reasoning enables predictive design of living materials
This article has been Reviewed by the following groups
Discuss this preprint
Start a discussion What are Sciety discussions?Listed in
- Evaluated articles (Arcadia Science)
Abstract
Living materials derive function from tightly coupled cellular and material processes to deliver adaptive and therapeutic capabilities, yet their predictive design remains constrained by fragmented, cross-disciplinary knowledge and experience-driven iteration. Here we introduce LiveMat, a multi-agent reasoning framework that reconstructs living materials as a computable design space from unstructured literature. LiveMat curates and standardizes 34,738 living-material records, integrating 16,086 microorganism entries and 18,682 polymer entries into a domain-scale knowledge graph comprising tens of thousands of entities and relationships. Through constraint-driven multi-agent reasoning and expert-anchored evaluation, the system converts implicit design heuristics into explicit, auditable rules. Comparative benchmarking across leading large language models shows that limitations in living materials reasoning arise primarily from cross-domain feature integration rather than coarse-grained classification. In a prospective acute wound-healing task, LiveMat evaluates combinatorial four-component systems across six functional dimensions and identifies a top-ranked design whose in vivo performance matches state-of-the-art systems. LiveMat establishes a scalable reasoning infrastructure for cumulative, data-grounded living materials discovery.
Article activity feed
-
Here we introduce LiveMat, a multi-agent reasoning framework that transforms document-level scientific knowledge into a computable design space for living materials. A central output is a domain-scale living materials knowledge graph that integrates cellular traits, material properties and functional outcomes as queryable semantic structures, enabling constraint-driven retrieval, multi-objective ranking and cumulative reuse of fragmented evidence. LiveMat further incorporates expert-anchored, multi-dimensional evaluation, formalizing both positive and negative outcomes as explicit design constraints. Applied to acute wound healing, LiveMat prospectively identifies a composite living material whose experimental performance matches state-of-the-art systems. LiveMat establishes a generalizable methodological infrastructure for cumulative …
Here we introduce LiveMat, a multi-agent reasoning framework that transforms document-level scientific knowledge into a computable design space for living materials. A central output is a domain-scale living materials knowledge graph that integrates cellular traits, material properties and functional outcomes as queryable semantic structures, enabling constraint-driven retrieval, multi-objective ranking and cumulative reuse of fragmented evidence. LiveMat further incorporates expert-anchored, multi-dimensional evaluation, formalizing both positive and negative outcomes as explicit design constraints. Applied to acute wound healing, LiveMat prospectively identifies a composite living material whose experimental performance matches state-of-the-art systems. LiveMat establishes a generalizable methodological infrastructure for cumulative living materials design and demonstrates how agentic AI can support scientific reasoning in cross-disciplinary domains constrained by fragmented evidence and heterogeneous evaluation regimes.
This is a really interesting project, and I appreciate this approach to the challenge of innovating in an expert-driven, interdisciplinary field. Two questions - who would you consider the audience for LiveMat, and how will you evaluate impact in the field of living materials design?
-
